csrhddlam/axial-deeplab
This is a PyTorch re-implementation of Axial-DeepLab (ECCV 2020 Spotlight)
PythonApache-2.0
Issues
- 0
Can it be used in video tasks?
#35 opened by lzl2040 - 0
Different resolution for inference
#34 opened by ChristophReich1996 - 0
why batchnormalization after qkv transform?
#33 opened by lkqnaruto - 13
This repo is mentioned for classification only, so it cant be used to semantic segmentation yet?
#10 opened by shrutishrestha - 15
Segmentation
#14 opened by SwagatRanjit84 - 0
about function parameter “s=0.5” in code
#32 opened by xxgh - 1
Pretrain_weights
#31 opened by NekonekoHu - 2
About local constraints
#30 opened by YLFF - 4
- 1
关于AxialAttention中kernel_size的问题
#28 opened by pengweiweiwei - 1
- 1
Shape of relative position encoding r^q, r^k, r^v
#29 opened by mcahny - 2
Question about Axial-Res50
#27 opened by lxa9867 - 1
Training with non-square images
#25 opened by dervirvel - 3
Question about table 9 in paper
#23 opened by CoinCheung - 1
What's HERE??
#24 opened by wanghao9610 - 3
Pretrained weights
#20 opened by Shujun-He - 1
- 1
- 2
- 1
position-sensitive attention
#17 opened by fmu2 - 2
size error
#8 opened by shrutishrestha - 3
About the class activation map
#16 opened by DesertsP - 3
span sizes
#15 opened by amhsinyednap - 3
Pretrained weights
#3 opened by netw0rkf10w - 5
- 4
Regarding the dimension of query and key
#11 opened by netw0rkf10w - 1
- 10
Strange runtime results
#2 opened by cszer - 1
model train error
#9 opened by shrutishrestha - 5
- 2
Relative Positional Encoding
#4 opened by romulus0914